Rather than print the full data set, print a subset (20 records) or view the table in SAS instead of PROC PRINT. proc print data=have(obs=20); run; ... View more

/*Why not PROC PLAN ?*/ DATA random; call streaminit(123); DO Subject = 1 to 60; number1 = RANUNI(5); number2 = RANUNI(5); OUTPUT; END; RUN; PROC RANK DATA = random OUT = ranked(index=(numrank1)) groups=2; VAR number1; RANKS numrank1; RUN; PROC RANK DATA = ranked OUT = ranked2 groups=2; by numrank1; VAR number2; RANKS numrank2; RUN; proc freq data=ranked2; table numrank1*numrank2/list; run; ... View more

To combine all of the datasets horizontally, you need to use a MERGE statement instead of a SET statement: *now merge all together; data allyears; merge year0 year1 year2; BY newid; RUN; ... View more

Wow thank you, that worked exactly like I needed it!  ... View more

Thank you for your quick reply, NA were indeed missing values and that solution worked perfectly!  ... View more

First thing about dealing with percentages: If your samples for each percentage are not the exact same then "mean" of a percentage is a misnomer at best and an outright lie at worst. Consider if a percentage of 15% is based on a population of 10,000 (1500/10000) and a second percentage of 13% is based on a population of 100 (13/100) when you average 15 and 13 you get 14. But the true percentage of the two groups combined is (1500 +13)/(10000+100) = 14.9802 %(rounded to 4 decimal places.   You may be better off with the data before you calculated means to get some of those summaries.     ... View more